Many data analysis problems can be cast as distance geometry problems in \emph{space forms} -- Euclidean, spherical, or hyperbolic spaces. Often, absolute distance measurements are often unreliable or simply unavailable and only proxies to absolute distances in the form of similarities are available. Hence we ask the following: Given only \emph{comparisons} of similarities amongst a set of entities, what can be said about the geometry of the underlying space form? To study this question, we introduce the notions of the \textit{ordinal capacity} of a target space form and \emph{ordinal spread} of the similarity measurements. The latter is an indicator of complex patterns in the measurements, while the former quantifies the capacity of a space form to accommodate a set of measurements with a specific ordinal spread profile. We prove that the ordinal capacity of a space form is related to its dimension and the sign of its curvature. This leads to a lower bound on the Euclidean and spherical embedding dimension of what we term similarity graphs. More importantly, we show that the statistical behavior of the ordinal spread random variables defined on a similarity graph can be used to identify its underlying space form. We support our theoretical claims with experiments on weighted trees, single-cell RNA expression data and spherical cartographic measurements.
Comparison of brain connectomes using geodesic distance on manifold:a twin study
Istituto Italiano di Tecnologia(意大利技术研究院);Università degli Studi di Genova(热那亚大学);Scientific Institute IRCCS “E. Medea”(IRCCS“E. Medea”科学研究所);Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico(IRCCS Ca’ Granda马焦雷医院基金会);Università di Milano(米兰大学);Università di Verona(维罗纳大学);Wayne State University(韦恩州立大学);Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会)
From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
Computational Modelling Lab, Humboldt-Universität zu Berlin, Berlin, Germany(洪堡-柏林大学计算建模实验室);Department of Education and Psychology, Freie Universität Berlin, Berlin, Germany(柏林自由大学教育与心理学系);Department for AI in Society, Science, and Technology, Zuse Institute Berlin, Germany(柏林祖克研究所人工智能与社会、科学与技术部门);Institute of Mathematics, Technische Universitat Berlin, Germany(柏林技术大学数学研究所)
Barycentric alignment for instance-level comparison of neural representations
Department of XXX, University of YYY, Location, Country(YYY大学XXX系);School of ZZZ, Institute of WWW, Location, Country(WWW研究所ZZZ学院);Department of Electrical and Computer Engineering, UCSD(UCSD电子与计算机工程系);Cognitive Science Department, UCSD(UCSD认知科学系);Department of Computer Science(计算机科学系)
Measuring the Measures: Discriminative Capacity of Representational Similarity Metrics Across Model Families
Department of Computer Science and Engineering, UC San Diego(计算机科学与工程系,UC San Diego);Department of Electrical and Computer Engineering, UC San Diego(电气与计算机工程系,UC San Diego);Department of Cognitive Science, UC San Diego(认知科学系,UC San Diego)
Forensic Study of Paintings Through the Comparison of Fabrics
Dep. Signal Processing and Communications, ETSi Universidad de Sevilla(信号处理与通信系,塞维利亚大学);Dep. Signal Processing and Communications, Universidad Carlos III de Madrid(信号处理与通信系,卡洛斯三世大学);Gabinete Técnico, Museo Nacional del Prado(技术办公室,普拉多国家博物馆)
本文提出一种基于Siamese深度学习的画布织物相似度评估方法,无需依赖线密度图即可比较非相邻画布,在Museo Nacional del Prado数据上验证了其可行性与准确性。